X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fbuffer.c;h=263f88e4dffb8bcd617742374d0934d316be948f;hb=58637ec90b7ceed5909e726ac90118852f79d2b1;hp=13e5938a64f6338072e06c16ad8b73e366cad024;hpb=152becd26e0563aefdbc4fd1fe491928efe92d1f;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/buffer.c b/fs/buffer.c index 13e5938..263f88e 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -18,7 +18,6 @@ * async buffer flushing, 1999 Andrea Arcangeli */ -#include #include #include #include @@ -26,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -35,11 +35,13 @@ #include #include #include +#include #include #include #include #include #include +#include static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static void invalidate_bh_lrus(void); @@ -95,7 +97,7 @@ static void __clear_page_buffers(struct page *page) { ClearPagePrivate(page); - page->private = 0; + set_page_private(page, 0); page_cache_release(page); } @@ -152,41 +154,14 @@ int sync_blockdev(struct block_device *bdev) { int ret = 0; - if (bdev) { - int err; - - ret = filemap_fdatawrite(bdev->bd_inode->i_mapping); - err = filemap_fdatawait(bdev->bd_inode->i_mapping); - if (!ret) - ret = err; - } + if (bdev) + ret = filemap_write_and_wait(bdev->bd_inode->i_mapping); return ret; } EXPORT_SYMBOL(sync_blockdev); /* * Write out and wait upon all dirty data associated with this - * superblock. Filesystem data as well as the underlying block - * device. Takes the superblock lock. - */ -int fsync_super(struct super_block *sb) -{ - sync_inodes_sb(sb, 0); - DQUOT_SYNC(sb); - lock_super(sb); - if (sb->s_dirt && sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - sync_blockdev(sb->s_bdev); - sync_inodes_sb(sb, 1); - - return sync_blockdev(sb->s_bdev); -} - -/* - * Write out and wait upon all dirty data associated with this * device. Filesystem data as well as the underlying block * device. Takes the superblock lock. */ @@ -205,7 +180,7 @@ int fsync_bdev(struct block_device *bdev) * freeze_bdev -- lock a filesystem and force it into a consistent state * @bdev: blockdevice to lock * - * This takes the block device bd_mount_sem to make sure no new mounts + * This takes the block device bd_mount_mutex to make sure no new mounts * happen on bdev until thaw_bdev() is called. * If a superblock is found on this device, we take the s_umount semaphore * on it to make sure nobody unmounts until the snapshot creation is done. @@ -214,25 +189,13 @@ struct super_block *freeze_bdev(struct block_device *bdev) { struct super_block *sb; - down(&bdev->bd_mount_sem); + mutex_lock(&bdev->bd_mount_mutex); sb = get_super(bdev); if (sb && !(sb->s_flags & MS_RDONLY)) { sb->s_frozen = SB_FREEZE_WRITE; smp_wmb(); - sync_inodes_sb(sb, 0); - DQUOT_SYNC(sb); - - lock_super(sb); - if (sb->s_dirt && sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - - if (sb->s_op->sync_fs) - sb->s_op->sync_fs(sb, 1); - - sync_blockdev(sb->s_bdev); - sync_inodes_sb(sb, 1); + __fsync_super(sb); sb->s_frozen = SB_FREEZE_TRANS; smp_wmb(); @@ -268,122 +231,11 @@ void thaw_bdev(struct block_device *bdev, struct super_block *sb) drop_super(sb); } - up(&bdev->bd_mount_sem); + mutex_unlock(&bdev->bd_mount_mutex); } EXPORT_SYMBOL(thaw_bdev); /* - * sync everything. Start out by waking pdflush, because that writes back - * all queues in parallel. - */ -static void do_sync(unsigned long wait) -{ - wakeup_bdflush(0); - sync_inodes(0); /* All mappings, inodes and their blockdevs */ - DQUOT_SYNC(NULL); - sync_supers(); /* Write the superblocks */ - sync_filesystems(0); /* Start syncing the filesystems */ - sync_filesystems(wait); /* Waitingly sync the filesystems */ - sync_inodes(wait); /* Mappings, inodes and blockdevs, again. */ - if (!wait) - printk("Emergency Sync complete\n"); - if (unlikely(laptop_mode)) - laptop_sync_completion(); -} - -asmlinkage long sys_sync(void) -{ - do_sync(1); - return 0; -} - -void emergency_sync(void) -{ - pdflush_operation(do_sync, 0); -} - -/* - * Generic function to fsync a file. - * - * filp may be NULL if called via the msync of a vma. - */ - -int file_fsync(struct file *filp, struct dentry *dentry, int datasync) -{ - struct inode * inode = dentry->d_inode; - struct super_block * sb; - int ret, err; - - /* sync the inode to buffers */ - ret = write_inode_now(inode, 0); - - /* sync the superblock to buffers */ - sb = inode->i_sb; - lock_super(sb); - if (sb->s_op->write_super) - sb->s_op->write_super(sb); - unlock_super(sb); - - /* .. finally sync the buffers to disk */ - err = sync_blockdev(sb->s_bdev); - if (!ret) - ret = err; - return ret; -} - -static long do_fsync(unsigned int fd, int datasync) -{ - struct file * file; - struct address_space *mapping; - int ret, err; - - ret = -EBADF; - file = fget(fd); - if (!file) - goto out; - - ret = -EINVAL; - if (!file->f_op || !file->f_op->fsync) { - /* Why? We can still call filemap_fdatawrite */ - goto out_putf; - } - - mapping = file->f_mapping; - - current->flags |= PF_SYNCWRITE; - ret = filemap_fdatawrite(mapping); - - /* - * We need to protect against concurrent writers, - * which could cause livelocks in fsync_buffers_list - */ - down(&mapping->host->i_sem); - err = file->f_op->fsync(file, file->f_dentry, datasync); - if (!ret) - ret = err; - up(&mapping->host->i_sem); - err = filemap_fdatawait(mapping); - if (!ret) - ret = err; - current->flags &= ~PF_SYNCWRITE; - -out_putf: - fput(file); -out: - return ret; -} - -asmlinkage long sys_fsync(unsigned int fd) -{ - return do_fsync(fd, 0); -} - -asmlinkage long sys_fdatasync(unsigned int fd) -{ - return do_fsync(fd, 1); -} - -/* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's @@ -395,7 +247,7 @@ asmlinkage long sys_fdatasync(unsigned int fd) * private_lock is contended then so is mapping->tree_lock). */ static struct buffer_head * -__find_get_block_slow(struct block_device *bdev, sector_t block, int unused) +__find_get_block_slow(struct block_device *bdev, sector_t block) { struct inode *bd_inode = bdev->bd_inode; struct address_space *bd_mapping = bd_inode->i_mapping; @@ -435,8 +287,10 @@ __find_get_block_slow(struct block_device *bdev, sector_t block, int unused) if (all_mapped) { printk("__find_get_block_slow() failed. " "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%u\n", bh->b_state, bh->b_size); + (unsigned long long)block, + (unsigned long long)bh->b_blocknr); + printk("b_state=0x%08lx, b_size=%zu\n", + bh->b_state, bh->b_size); printk("device blocksize: %d\n", 1 << bd_inode->i_blkbits); } out_unlock: @@ -480,13 +334,18 @@ out: pass does the actual I/O. */ void invalidate_bdev(struct block_device *bdev, int destroy_dirty_buffers) { + struct address_space *mapping = bdev->bd_inode->i_mapping; + + if (mapping->nrpages == 0) + return; + invalidate_bh_lrus(); /* * FIXME: what about destroy_dirty_buffers? * We really want to use invalidate_inode_pages2() for * that, but not until that's cleaned up. */ - invalidate_inode_pages(bdev->bd_inode->i_mapping); + invalidate_inode_pages(mapping); } /* @@ -497,11 +356,11 @@ static void free_more_memory(void) struct zone **zones; pg_data_t *pgdat; - wakeup_bdflush(1024); + wakeup_pdflush(1024); yield(); - for_each_pgdat(pgdat) { - zones = pgdat->node_zonelists[GFP_NOFS&GFP_ZONEMASK].zones; + for_each_online_pgdat(pgdat) { + zones = pgdat->node_zonelists[gfp_zone(GFP_NOFS)].zones; if (*zones) try_to_free_pages(zones, GFP_NOFS); } @@ -513,8 +372,8 @@ static void free_more_memory(void) */ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { - static DEFINE_SPINLOCK(page_uptodate_lock); unsigned long flags; + struct buffer_head *first; struct buffer_head *tmp; struct page *page; int page_uptodate = 1; @@ -536,7 +395,9 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ - spin_lock_irqsave(&page_uptodate_lock, flags); + first = page_buffers(page); + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &first->b_state); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; @@ -549,7 +410,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } while (tmp != bh); - spin_unlock_irqrestore(&page_uptodate_lock, flags); + bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); + local_irq_restore(flags); /* * If none of the buffers had errors and they are all @@ -561,7 +423,8 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate) return; still_busy: - spin_unlock_irqrestore(&page_uptodate_lock, flags); + bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); + local_irq_restore(flags); return; } @@ -569,11 +432,11 @@ still_busy: * Completion handler for block_write_full_page() - pages which are unlocked * during I/O, and which have PageWriteback cleared upon I/O completion. */ -void end_buffer_async_write(struct buffer_head *bh, int uptodate) +static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { char b[BDEVNAME_SIZE]; - static DEFINE_SPINLOCK(page_uptodate_lock); unsigned long flags; + struct buffer_head *first; struct buffer_head *tmp; struct page *page; @@ -590,11 +453,15 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) bdevname(bh->b_bdev, b)); } set_bit(AS_EIO, &page->mapping->flags); + set_buffer_write_io_error(bh); clear_buffer_uptodate(bh); SetPageError(page); } - spin_lock_irqsave(&page_uptodate_lock, flags); + first = page_buffers(page); + local_irq_save(flags); + bit_spin_lock(BH_Uptodate_Lock, &first->b_state); + clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; @@ -605,12 +472,14 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate) } tmp = tmp->b_this_page; } - spin_unlock_irqrestore(&page_uptodate_lock, flags); + bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); + local_irq_restore(flags); end_page_writeback(page); return; still_busy: - spin_unlock_irqrestore(&page_uptodate_lock, flags); + bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); + local_irq_restore(flags); return; } @@ -704,6 +573,10 @@ EXPORT_SYMBOL(mark_buffer_async_write); static inline void __remove_assoc_queue(struct buffer_head *bh) { list_del_init(&bh->b_assoc_buffers); + WARN_ON(!bh->b_assoc_map); + if (buffer_write_io_error(bh)) + set_bit(AS_EIO, &bh->b_assoc_map->flags); + bh->b_assoc_map = NULL; } int inode_has_buffers(struct inode *inode) @@ -796,13 +669,13 @@ void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) if (!mapping->assoc_mapping) { mapping->assoc_mapping = buffer_mapping; } else { - if (mapping->assoc_mapping != buffer_mapping) - BUG(); + BUG_ON(mapping->assoc_mapping != buffer_mapping); } if (list_empty(&bh->b_assoc_buffers)) { spin_lock(&buffer_mapping->private_lock); list_move_tail(&bh->b_assoc_buffers, &mapping->private_list); + bh->b_assoc_map = mapping; spin_unlock(&buffer_mapping->private_lock); } } @@ -835,7 +708,10 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode); */ int __set_page_dirty_buffers(struct page *page) { - struct address_space * const mapping = page->mapping; + struct address_space * const mapping = page_mapping(page); + + if (unlikely(!mapping)) + return !TestSetPageDirty(page); spin_lock(&mapping->private_lock); if (page_has_buffers(page)) { @@ -849,20 +725,21 @@ int __set_page_dirty_buffers(struct page *page) } spin_unlock(&mapping->private_lock); - if (!TestSetPageDirty(page)) { - write_lock_irq(&mapping->tree_lock); - if (page->mapping) { /* Race with truncate? */ - if (mapping_cap_account_dirty(mapping)) - inc_page_state(nr_dirty); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); + if (TestSetPageDirty(page)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (page->mapping) { /* Race with truncate? */ + if (mapping_cap_account_dirty(mapping)) { + __inc_zone_page_state(page, NR_FILE_DIRTY); + task_io_account_write(PAGE_CACHE_SIZE); } - write_unlock_irq(&mapping->tree_lock); - __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); } - - return 0; + write_unlock_irq(&mapping->tree_lock); + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); + return 1; } EXPORT_SYMBOL(__set_page_dirty_buffers); @@ -896,7 +773,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) spin_lock(lock); while (!list_empty(list)) { bh = BH_ENTRY(list->next); - list_del_init(&bh->b_assoc_buffers); + __remove_assoc_queue(bh); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); if (buffer_dirty(bh)) { @@ -908,8 +785,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) * contents - it is a noop if I/O is still in * flight on potentially older contents. */ - wait_on_buffer(bh); - ll_rw_block(WRITE, 1, &bh); + ll_rw_block(SWRITE, 1, &bh); brelse(bh); spin_lock(lock); } @@ -918,7 +794,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); - __remove_assoc_queue(bh); + list_del_init(&bh->b_assoc_buffers); get_bh(bh); spin_unlock(lock); wait_on_buffer(bh); @@ -1018,12 +894,13 @@ try_again: bh->b_state = 0; atomic_set(&bh->b_count, 0); + bh->b_private = NULL; bh->b_size = size; /* Link the buffer to its page */ set_bh_page(bh, page, offset); - bh->b_end_io = NULL; + init_buffer(bh, NULL, NULL); } return head; /* @@ -1114,8 +991,7 @@ grow_dev_page(struct block_device *bdev, sector_t block, if (!page) return NULL; - if (!PageLocked(page)) - BUG(); + BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); @@ -1161,7 +1037,7 @@ failed: * some of those buffers may be aliases of filesystem data. * grow_dev_page() will go BUG() if this happens. */ -static inline int +static int grow_buffers(struct block_device *bdev, sector_t block, int size) { struct page *page; @@ -1174,8 +1050,21 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) } while ((size << sizebits) < PAGE_SIZE); index = block >> sizebits; - block = index << sizebits; + /* + * Check for a block which wants to lie outside our maximum possible + * pagecache index. (this comparison is done using sector_t types). + */ + if (unlikely(index != block >> sizebits)) { + char b[BDEVNAME_SIZE]; + + printk(KERN_ERR "%s: requested out-of-range block %llu for " + "device %s\n", + __FUNCTION__, (unsigned long long)block, + bdevname(bdev, b)); + return -EIO; + } + block = index << sizebits; /* Create a page with the proper size buffers.. */ page = grow_dev_page(bdev, block, index, size); if (!page) @@ -1202,12 +1091,16 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) for (;;) { struct buffer_head * bh; + int ret; bh = __find_get_block(bdev, block, size); if (bh) return bh; - if (!grow_buffers(bdev, block, size)) + ret = grow_buffers(bdev, block, size); + if (ret < 0) + return NULL; + if (ret == 0) free_more_memory(); } } @@ -1282,6 +1175,7 @@ void __bforget(struct buffer_head *bh) spin_lock(&buffer_mapping->private_lock); list_del_init(&bh->b_assoc_buffers); + bh->b_assoc_map = NULL; spin_unlock(&buffer_mapping->private_lock); } __brelse(bh); @@ -1387,7 +1281,7 @@ static void bh_lru_install(struct buffer_head *bh) /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ -static inline struct buffer_head * +static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, int size) { struct buffer_head *ret = NULL; @@ -1429,7 +1323,7 @@ __find_get_block(struct block_device *bdev, sector_t block, int size) struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { - bh = __find_get_block_slow(bdev, block, size); + bh = __find_get_block_slow(bdev, block); if (bh) bh_lru_install(bh); } @@ -1469,8 +1363,10 @@ EXPORT_SYMBOL(__getblk); void __breadahead(struct block_device *bdev, sector_t block, int size) { struct buffer_head *bh = __getblk(bdev, block, size); - ll_rw_block(READA, 1, &bh); - brelse(bh); + if (likely(bh)) { + ll_rw_block(READA, 1, &bh); + brelse(bh); + } } EXPORT_SYMBOL(__breadahead); @@ -1488,7 +1384,7 @@ __bread(struct block_device *bdev, sector_t block, int size) { struct buffer_head *bh = __getblk(bdev, block, size); - if (!buffer_uptodate(bh)) + if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } @@ -1520,8 +1416,7 @@ void set_bh_page(struct buffer_head *bh, struct page *page, unsigned long offset) { bh->b_page = page; - if (offset >= PAGE_SIZE) - BUG(); + BUG_ON(offset >= PAGE_SIZE); if (PageHighMem(page)) /* * This catches illegal uses and preserves the offset: @@ -1535,7 +1430,7 @@ EXPORT_SYMBOL(set_bh_page); /* * Called when truncating a buffer on a page completely. */ -static inline void discard_buffer(struct buffer_head * bh) +static void discard_buffer(struct buffer_head * bh) { lock_buffer(bh); clear_buffer_dirty(bh); @@ -1548,35 +1443,6 @@ static inline void discard_buffer(struct buffer_head * bh) } /** - * try_to_release_page() - release old fs-specific metadata on a page - * - * @page: the page which the kernel is trying to free - * @gfp_mask: memory allocation flags (and I/O mode) - * - * The address_space is to try to release any data against the page - * (presumably at page->private). If the release was successful, return `1'. - * Otherwise return zero. - * - * The @gfp_mask argument specifies whether I/O may be performed to release - * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). - * - * NOTE: @gfp_mask may go away, and this function may become non-blocking. - */ -int try_to_release_page(struct page *page, int gfp_mask) -{ - struct address_space * const mapping = page->mapping; - - BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) - return 0; - - if (mapping && mapping->a_ops->releasepage) - return mapping->a_ops->releasepage(page, gfp_mask); - return try_to_free_buffers(page); -} -EXPORT_SYMBOL(try_to_release_page); - -/** * block_invalidatepage - invalidate part of all of a buffer-backed page * * @page: the page which is affected @@ -1591,11 +1457,10 @@ EXPORT_SYMBOL(try_to_release_page); * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ -int block_invalidatepage(struct page *page, unsigned long offset) +void block_invalidatepage(struct page *page, unsigned long offset) { struct buffer_head *head, *bh, *next; unsigned int curr_off = 0; - int ret = 1; BUG_ON(!PageLocked(page)); if (!page_has_buffers(page)) @@ -1622,9 +1487,9 @@ int block_invalidatepage(struct page *page, unsigned long offset) * so real IO is not possible anymore. */ if (offset == 0) - ret = try_to_release_page(page, 0); + try_to_release_page(page, 0); out: - return ret; + return; } EXPORT_SYMBOL(block_invalidatepage); @@ -1685,7 +1550,7 @@ void unmap_underlying_metadata(struct block_device *bdev, sector_t block) might_sleep(); - old_bh = __find_get_block_slow(bdev, block, 0); + old_bh = __find_get_block_slow(bdev, block); if (old_bh) { clear_buffer_dirty(old_bh); wait_on_buffer(old_bh); @@ -1727,6 +1592,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, sector_t block; sector_t last_block; struct buffer_head *bh, *head; + const unsigned blocksize = 1 << inode->i_blkbits; int nr_underway = 0; BUG_ON(!PageLocked(page)); @@ -1734,7 +1600,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, last_block = (i_size_read(inode) - 1) >> inode->i_blkbits; if (!page_has_buffers(page)) { - create_empty_buffers(page, 1 << inode->i_blkbits, + create_empty_buffers(page, blocksize, (1 << BH_Dirty)|(1 << BH_Uptodate)); } @@ -1748,7 +1614,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, * handle that here by just cleaning them. */ - block = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + block = (sector_t)page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits); head = page_buffers(page); bh = head; @@ -1769,6 +1635,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page, clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if (!buffer_mapped(bh) && buffer_dirty(bh)) { + WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; @@ -1922,6 +1789,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page, if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) break; @@ -1995,6 +1863,7 @@ static int __block_prepare_write(struct inode *inode, struct page *page, clear_buffer_new(bh); kaddr = kmap_atomic(page, KM_USER0); memset(kaddr+block_start, 0, bh->b_size); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); set_buffer_uptodate(bh); mark_buffer_dirty(bh); @@ -2077,6 +1946,7 @@ int block_read_full_page(struct page *page, get_block_t *get_block) fully_mapped = 0; if (iblock < lblock) { + WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) SetPageError(page); @@ -2140,11 +2010,12 @@ int block_read_full_page(struct page *page, get_block_t *get_block) * truncates. Uses prepare/commit_write to allow the filesystem to * deal with the hole. */ -int generic_cont_expand(struct inode *inode, loff_t size) +static int __generic_cont_expand(struct inode *inode, loff_t size, + pgoff_t index, unsigned int offset) { struct address_space *mapping = inode->i_mapping; struct page *page; - unsigned long index, offset, limit; + unsigned long limit; int err; err = -EFBIG; @@ -2156,24 +2027,24 @@ int generic_cont_expand(struct inode *inode, loff_t size) if (size > inode->i_sb->s_maxbytes) goto out; - offset = (size & (PAGE_CACHE_SIZE-1)); /* Within page */ - - /* ugh. in prepare/commit_write, if from==to==start of block, we - ** skip the prepare. make sure we never send an offset for the start - ** of a block - */ - if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) { - offset++; - } - index = size >> PAGE_CACHE_SHIFT; err = -ENOMEM; page = grab_cache_page(mapping, index); if (!page) goto out; err = mapping->a_ops->prepare_write(NULL, page, offset, offset); - if (!err) { - err = mapping->a_ops->commit_write(NULL, page, offset, offset); + if (err) { + /* + * ->prepare_write() may have instantiated a few blocks + * outside i_size. Trim these off again. + */ + unlock_page(page); + page_cache_release(page); + vmtruncate(inode, inode->i_size); + goto out; } + + err = mapping->a_ops->commit_write(NULL, page, offset, offset); + unlock_page(page); page_cache_release(page); if (err > 0) @@ -2182,6 +2053,36 @@ out: return err; } +int generic_cont_expand(struct inode *inode, loff_t size) +{ + pgoff_t index; + unsigned int offset; + + offset = (size & (PAGE_CACHE_SIZE - 1)); /* Within page */ + + /* ugh. in prepare/commit_write, if from==to==start of block, we + ** skip the prepare. make sure we never send an offset for the start + ** of a block + */ + if ((offset & (inode->i_sb->s_blocksize - 1)) == 0) { + /* caller must handle this extra byte. */ + offset++; + } + index = size >> PAGE_CACHE_SHIFT; + + return __generic_cont_expand(inode, size, index, offset); +} + +int generic_cont_expand_simple(struct inode *inode, loff_t size) +{ + loff_t pos = size - 1; + pgoff_t index = pos >> PAGE_CACHE_SHIFT; + unsigned int offset = (pos & (PAGE_CACHE_SIZE - 1)) + 1; + + /* prepare/commit_write can handle even if from==to==start of block. */ + return __generic_cont_expand(inode, size, index, offset); +} + /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. @@ -2293,7 +2194,7 @@ int generic_commit_write(struct file *file, struct page *page, __block_commit_write(inode,page,from,to); /* * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_sem. + * cannot change under us because we hold i_mutex. */ if (pos > inode->i_size) { i_size_write(inode, pos); @@ -2367,6 +2268,7 @@ int nobh_prepare_write(struct page *page, unsigned from, unsigned to, create = 1; if (block_start >= to) create = 0; + map_bh.b_size = blocksize; ret = get_block(inode, block_in_file + block_in_page, &map_bh, create); if (ret) @@ -2468,6 +2370,7 @@ failed: */ kaddr = kmap_atomic(page, KM_USER0); memset(kaddr, 0, PAGE_CACHE_SIZE); + flush_dcache_page(page); kunmap_atomic(kaddr, KM_USER0); SetPageUptodate(page); set_page_dirty(page); @@ -2556,7 +2459,7 @@ int nobh_truncate_page(struct address_space *mapping, loff_t from) unsigned offset = from & (PAGE_CACHE_SIZE-1); unsigned to; struct page *page; - struct address_space_operations *a_ops = mapping->a_ops; + const struct address_space_operations *a_ops = mapping->a_ops; char *kaddr; int ret = 0; @@ -2590,7 +2493,7 @@ int block_truncate_page(struct address_space *mapping, pgoff_t index = from >> PAGE_CACHE_SHIFT; unsigned offset = from & (PAGE_CACHE_SIZE-1); unsigned blocksize; - pgoff_t iblock; + sector_t iblock; unsigned length, pos; struct inode *inode = mapping->host; struct page *page; @@ -2606,7 +2509,7 @@ int block_truncate_page(struct address_space *mapping, return 0; length = blocksize - length; - iblock = index << (PAGE_CACHE_SHIFT - inode->i_blkbits); + iblock = (sector_t)index << (PAGE_CACHE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); err = -ENOMEM; @@ -2627,6 +2530,7 @@ int block_truncate_page(struct address_space *mapping, err = 0; if (!buffer_mapped(bh)) { + WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; @@ -2687,7 +2591,7 @@ int block_write_full_page(struct page *page, get_block_t *get_block, * they may have been added in ext3_writepage(). Make them * freeable here, so the page does not leak. */ - block_invalidatepage(page, 0); + do_invalidatepage(page, 0); unlock_page(page); return 0; /* don't care */ } @@ -2713,6 +2617,7 @@ sector_t generic_block_bmap(struct address_space *mapping, sector_t block, struct inode *inode = mapping->host; tmp.b_state = 0; tmp.b_blocknr = 0; + tmp.b_size = 1 << inode->i_blkbits; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } @@ -2784,21 +2689,22 @@ int submit_bh(int rw, struct buffer_head * bh) /** * ll_rw_block: low-level access to block devices (DEPRECATED) - * @rw: whether to %READ or %WRITE or maybe %READA (readahead) + * @rw: whether to %READ or %WRITE or %SWRITE or maybe %READA (readahead) * @nr: number of &struct buffer_heads in the array * @bhs: array of pointers to &struct buffer_head * - * ll_rw_block() takes an array of pointers to &struct buffer_heads, - * and requests an I/O operation on them, either a %READ or a %WRITE. - * The third %READA option is described in the documentation for - * generic_make_request() which ll_rw_block() calls. + * ll_rw_block() takes an array of pointers to &struct buffer_heads, and + * requests an I/O operation on them, either a %READ or a %WRITE. The third + * %SWRITE is like %WRITE only we make sure that the *current* data in buffers + * are sent to disk. The fourth %READA option is described in the documentation + * for generic_make_request() which ll_rw_block() calls. * * This function drops any buffer that it cannot get a lock on (with the - * BH_Lock state bit), any buffer that appears to be clean when doing a - * write request, and any buffer that appears to be up-to-date when doing - * read request. Further it marks as clean buffers that are processed for - * writing (the buffer cache won't assume that they are actually clean until - * the buffer gets unlocked). + * BH_Lock state bit) unless SWRITE is required, any buffer that appears to be + * clean when doing a write request, and any buffer that appears to be + * up-to-date when doing read request. Further it marks as clean buffers that + * are processed for writing (the buffer cache won't assume that they are + * actually clean until the buffer gets unlocked). * * ll_rw_block sets b_end_io to simple completion handler that marks * the buffer up-to-date (if approriate), unlocks the buffer and wakes @@ -2814,25 +2720,27 @@ void ll_rw_block(int rw, int nr, struct buffer_head *bhs[]) for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; - if (test_set_buffer_locked(bh)) + if (rw == SWRITE) + lock_buffer(bh); + else if (test_set_buffer_locked(bh)) continue; - get_bh(bh); - if (rw == WRITE) { + if (rw == WRITE || rw == SWRITE) { if (test_clear_buffer_dirty(bh)) { bh->b_end_io = end_buffer_write_sync; + get_bh(bh); submit_bh(WRITE, bh); continue; } } else { if (!buffer_uptodate(bh)) { bh->b_end_io = end_buffer_read_sync; + get_bh(bh); submit_bh(rw, bh); continue; } } unlock_buffer(bh); - put_bh(bh); } } @@ -2926,7 +2834,7 @@ int try_to_free_buffers(struct page *page) int ret = 0; BUG_ON(!PageLocked(page)); - if (PageWriteback(page)) + if (PageDirty(page) || PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ @@ -2936,17 +2844,6 @@ int try_to_free_buffers(struct page *page) spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); - if (ret) { - /* - * If the filesystem writes its buffers by hand (eg ext3) - * then we can have clean buffers against a dirty page. We - * clean the page here; otherwise later reattachment of buffers - * could encounter a non-uptodate page, which is unresolvable. - * This only applies in the rare case where try_to_free_buffers - * succeeds but the page is not freed. - */ - clear_page_dirty(page); - } spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { @@ -2962,7 +2859,7 @@ out: } EXPORT_SYMBOL(try_to_free_buffers); -int block_sync_page(struct page *page) +void block_sync_page(struct page *page) { struct address_space *mapping; @@ -2970,7 +2867,6 @@ int block_sync_page(struct page *page) mapping = page_mapping(page); if (mapping) blk_run_backing_dev(mapping->backing_dev_info, page); - return 0; } /* @@ -3003,7 +2899,7 @@ asmlinkage long sys_bdflush(int func, long data) /* * Buffer-head allocation */ -static kmem_cache_t *bh_cachep; +static struct kmem_cache *bh_cachep; /* * Once the number of bh's in the machine exceeds this level, we start @@ -3028,19 +2924,18 @@ static void recalc_bh_state(void) if (__get_cpu_var(bh_accounting).ratelimit++ < 4096) return; __get_cpu_var(bh_accounting).ratelimit = 0; - for_each_cpu(i) + for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } -struct buffer_head *alloc_buffer_head(unsigned int __nocast gfp_flags) +struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_alloc(bh_cachep, gfp_flags); if (ret) { - preempt_disable(); - __get_cpu_var(bh_accounting).nr++; + get_cpu_var(bh_accounting).nr++; recalc_bh_state(); - preempt_enable(); + put_cpu_var(bh_accounting); } return ret; } @@ -3050,15 +2945,14 @@ void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); - preempt_disable(); - __get_cpu_var(bh_accounting).nr--; + get_cpu_var(bh_accounting).nr--; recalc_bh_state(); - preempt_enable(); + put_cpu_var(bh_accounting); } EXPORT_SYMBOL(free_buffer_head); static void -init_buffer_head(void *data, kmem_cache_t *cachep, unsigned long flags) +init_buffer_head(void *data, struct kmem_cache *cachep, unsigned long flags) { if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == SLAB_CTOR_CONSTRUCTOR) { @@ -3069,7 +2963,6 @@ init_buffer_head(void *data, kmem_cache_t *cachep, unsigned long flags) } } -#ifdef CONFIG_HOTPLUG_CPU static void buffer_exit_cpu(int cpu) { int i; @@ -3079,6 +2972,9 @@ static void buffer_exit_cpu(int cpu) brelse(b->bhs[i]); b->bhs[i] = NULL; } + get_cpu_var(bh_accounting).nr += per_cpu(bh_accounting, cpu).nr; + per_cpu(bh_accounting, cpu).nr = 0; + put_cpu_var(bh_accounting); } static int buffer_cpu_notify(struct notifier_block *self, @@ -3088,15 +2984,17 @@ static int buffer_cpu_notify(struct notifier_block *self, buffer_exit_cpu((unsigned long)hcpu); return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ void __init buffer_init(void) { int nrpages; bh_cachep = kmem_cache_create("buffer_head", - sizeof(struct buffer_head), 0, - SLAB_RECLAIM_ACCOUNT|SLAB_PANIC, init_buffer_head, NULL); + sizeof(struct buffer_head), 0, + (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| + SLAB_MEM_SPREAD), + init_buffer_head, + NULL); /* * Limit the bh occupancy to 10% of ZONE_NORMAL @@ -3116,7 +3014,6 @@ EXPORT_SYMBOL(block_sync_page); EXPORT_SYMBOL(block_truncate_page); EXPORT_SYMBOL(block_write_full_page); EXPORT_SYMBOL(cont_prepare_write); -EXPORT_SYMBOL(end_buffer_async_write); EXPORT_SYMBOL(end_buffer_read_sync); EXPORT_SYMBOL(end_buffer_write_sync); EXPORT_SYMBOL(file_fsync); @@ -3124,6 +3021,7 @@ EXPORT_SYMBOL(fsync_bdev); EXPORT_SYMBOL(generic_block_bmap); EXPORT_SYMBOL(generic_commit_write); EXPORT_SYMBOL(generic_cont_expand); +EXPORT_SYMBOL(generic_cont_expand_simple); EXPORT_SYMBOL(init_buffer); EXPORT_SYMBOL(invalidate_bdev); EXPORT_SYMBOL(ll_rw_block);